© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 11698
    Prev
    Next
    INDEX
    Explanations

    email structures and communication-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to emails or email communications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     idols
    -0.66
    Mods
    -0.65
    esses
    -0.65
    artifacts
    -0.64
    otin
    -0.63
    ãĥİ
    -0.63
    Os
    -0.62
    Tags
    -0.62
     Eggs
    -0.60
    addons
    -0.59
    POSITIVE LOGITS
     reply
    1.15
     response
    1.12
     statement
    1.07
     exchange
    1.04
     message
    1.00
     interview
    0.97
     request
    0.93
     correspondence
    0.89
     conversation
    0.89
     apology
    0.88
    Activations Density 0.073%

    No Known Activations